feat: CrewAI incident response example with KD6 memory backend - #6
Closed
devigned wants to merge 1 commit into
Closed
feat: CrewAI incident response example with KD6 memory backend#6devigned wants to merge 1 commit into
devigned wants to merge 1 commit into
Conversation
devigned
force-pushed
the
examples/crewai-memory
branch
7 times, most recently
from
June 3, 2026 21:50
b89cb67 to
e80bc24
Compare
Add examples/crewai-memory/ demonstrating CrewAI multi-agent crews using KD6 as a persistent, layered memory backend via the StorageBackend protocol. Components: - Kd6StorageBackend: full StorageBackend protocol adapter translating CrewAI's path-based scopes to KD6's structured MemoryScope hierarchy, with upsert-based idempotent saves and metadata envelope preservation - Incident response simulation: 4-agent crew (Incident Commander, Platform Engineer, Backend Developer, Communications Lead) investigating a production checkout service failure - Smoke test: non-LLM connectivity test validating all CRUD operations - GitHub Models integration: both LLM inference and embeddings via GITHUB_TOKEN with openai/gpt-4o-mini and text-embedding-3-small Also adds Python-specific entries to .gitignore (__pycache__, .venv, .env). Signed-off-by: David Justice <david@justice.dev>
devigned
force-pushed
the
examples/crewai-memory
branch
from
June 3, 2026 21:51
e80bc24 to
db6c6e5
Compare
Owner
Author
|
Closing — will reopen once fully validated locally. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
CrewAI multi-agent example using KD6 as the persistent memory backend via the
StorageBackendprotocol.What's Included
Kd6StorageBackend(src/kd6_backend.py)Full implementation of CrewAI's
StorageBackendprotocol:/org/team/agent) to KD6's structuredMemoryScopeupsert_keyfor idempotent saves with CrewAI record IDscontent.crewai_metadata)create_edge,traverse_graph) beyond the protocolIncident Response Simulation (
src/main.py)4-agent crew investigating a production incident at fictional "ShopStream":
GitHub Models Integration
Both LLM and embeddings use GitHub Models (
GITHUB_TOKEN):openai/gpt-4o-miniviahttps://models.github.ai/inferenceopenai/text-embedding-3-smallvia same endpointSmoke Test (
src/smoke_test.py)Non-LLM connectivity test validating all CRUD operations against a running KD6 server.
KD6 Features Demonstrated